TY  - UNPD
A1  - Herold, Ulf
A1  - Maurer, Raimond
T1  - How much foreign stocks? : classical versus Bayesian approaches to asset allocation
T2  - Goethe-Universität Frankfurt am Main. Fachbereich Wirtschaftswissenschaften: Working paper series / Finance & accounting ; No. 92
N2  - The classical approaches to asset allocation give very different conclusions about how much foreign stocks a US investor should hold. US investors should either allocate a large portion of about 40% to foreign stocks (which is the result of mean/variance optimization and the international CAPM) or they should hold no foreign stocks at all (which is the conclusion of the domestic CAPM and mean/variance spanning tests). There is no way in between.
The idea of the Bayesian approach discussed in this article is to shrink the mean/variance efficient portfolio towards the market portfolio. The shrinkage effect is determined by the investor's prior belief in the efficiency of the market portfolio and by the degree of violation of the CAPM in the sample. Interestingly, this Bayesian approach leads to the same implications for asset allocation as the mean-variance/tracking error criterion. In both cases, the optimal portfolio is a combination of the market portfolio and the mean/variance efficient portfolio with the highest Sharpe ratio.
Applying both approaches to the subject of international diversification, we find that a substantial home bias is only justified when a US investor has a strong belief in the global mean/variance efficiency of the US market portfolio and when he has a high regret aversion of falling behind the US market portfolio. We also find that the current level of home bias can be justified whenever-regret aversion is significantly higher than risk aversion.
Finally, we compare the Bayesian approach of shrinking the mean/variance efficient portfolio towards the market portfolio to another Bayesian approach which shrinks the mean/variance efficient portfolio towards the minimum-variance portfolio. An empirical out-of-sample study shows that both Bayesian approaches lead to a clearly superior performance compared to the classical mean/variance efficient portfolio.
T3  - Working paper series / Johann-Wolfgang-Goethe-Universität Frankfurt am Main, Fachbereich Wirtschaftswissenschaften : Finance & Accounting - 92 
KW  - portfolio selection
KW  - asset-pricing models
KW  - Bayesian inference
KW  - estimation risk
KW  - international diversification
KW  - Portfoliomanagement
KW  - Aktie
KW  - Capital-Asset-Pricing-Modell
KW  - Bayes-Regel
Y1  - 2003
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/26010
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-260106
SN  - 1434-3401
PB  - Goethe-Universität Frankfurt, Fachbereich Wirtschaftswissenschaften
CY  - Frankfurt am Main
ER  -